Hessian and approximated Hessian matrices in maximum likelihood estimation: a Monte Carlo study
Giorgio Calzolari and
MPRA Paper from University Library of Munich, Germany
Full information maximum likelihood estimation of econometric models, linear and nonlinear in variables, is performed by means of two gradient algorithms, using either the Hessian matrix or a computationally simpler approximation. In the first part of the paper, the behavior of the two methods in getting the optimum is investigated with Monte Carlo experimentation on some models of small and medium size. In the second part of the paper, the behavior of the two matrices in producing estimates of the asymptotic covariance matrix of coefficients is analyzed and, again. experimented with Monte Carlo on the same models. Some systematic differences are evidenced.
Keywords: Hessian matrix; full information maximum likelihood; Newton like methods; gradient methods; covariance matrix estimators (search for similar items in EconPapers)
JEL-codes: C63 C3 (search for similar items in EconPapers)
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (3) Track citations by RSS feed
Downloads: (external link)
https://mpra.ub.uni-muenchen.de/28847/1/MPRA_paper_28847.pdf original version (application/pdf)
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
Persistent link: https://EconPapers.repec.org/RePEc:pra:mprapa:28847
Access Statistics for this paper
More papers in MPRA Paper from University Library of Munich, Germany Ludwigstraße 33, D-80539 Munich, Germany. Contact information at EDIRC.
Bibliographic data for series maintained by Joachim Winter ().